{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NIVC4BKDEVTXFYRQP2QKGUARMI","short_pith_number":"pith:NIVC4BKD","canonical_record":{"source":{"id":"2606.07577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T19:12:13Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"cc55d665b8fa68c2d379f30007ee67a897b876aa0245867ffdb33481d8e1769c","abstract_canon_sha256":"e63a7397adf921b934661652e88878760bca9479d3114ff504e9e94606f34ca9"},"schema_version":"1.0"},"canonical_sha256":"6a2a2e0543256772e2307ea0a350116232fcb3963d1da5421ee45186fc6f9035","source":{"kind":"arxiv","id":"2606.07577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07577","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07577v1","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07577","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"NIVC4BKDEVTX","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"NIVC4BKDEVTXFYRQ","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"NIVC4BKD","created_at":"2026-06-09T00:04:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NIVC4BKDEVTXFYRQP2QKGUARMI","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T19:12:13Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"cc55d665b8fa68c2d379f30007ee67a897b876aa0245867ffdb33481d8e1769c","abstract_canon_sha256":"e63a7397adf921b934661652e88878760bca9479d3114ff504e9e94606f34ca9"},"schema_version":"1.0"},"canonical_sha256":"6a2a2e0543256772e2307ea0a350116232fcb3963d1da5421ee45186fc6f9035","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:43.566619Z","signature_b64":"IFk8Ordd0EHq+t6PufIpUnl2lDnahMgM1T+nJBCre3qX0LfEGWEZFh4ITlnE/QAYeR09xAUAPa7o/88QiuBpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a2a2e0543256772e2307ea0a350116232fcb3963d1da5421ee45186fc6f9035","last_reissued_at":"2026-06-09T00:04:43.565949Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:43.565949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07577","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T00:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3zl1HmPad/O38BQiObG+qjekmBvysyptZv+QqJ6HoCw2drBNPZsgiSUj0hpnDPlBSOVdf4mEU77Wful7Fiv1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T13:27:13.790097Z"},"content_sha256":"0a0d85fb2f14358444588f46abc8a1cd00c53bbc7e2a2a3bb5759d723f58add5","schema_version":"1.0","event_id":"sha256:0a0d85fb2f14358444588f46abc8a1cd00c53bbc7e2a2a3bb5759d723f58add5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NIVC4BKDEVTXFYRQP2QKGUARMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.AI","authors_text":"Chao Zhang, Guangzhi Sun, Yixuan Li, Yudong Yang","submitted_at":"2026-05-26T19:12:13Z","abstract_excerpt":"Audio-visual large language models (LLMs) hold strong promise for long-form video understanding, yet their long-video inference is fundamentally limited by the linear growth of video tokens and key-value (KV) caches. We present OmniMem, a memory-efficient streaming framework designed specifically for audio-visual LLMs. Unlike existing compression methods that treat all tokens uniformly, OmniMem introduces a modality-aware memory allocation strategy that separately manages visual and audio contexts, addressing the severe token imbalance between the two modalities. OmniMem further preserves info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07577","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.07577/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T00:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b6UrPDgvVXcODEyAa1zN8aoJAKfSPvAUi7cN4XcRbraGBPr2hLv2r0afxwJdLGICr9bMrP8uzFEWiekXKa19Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T13:27:13.790761Z"},"content_sha256":"a3d5c83188bee7c6d60caca56029f2751645f8e904190a8a8ba99a45aa3fb1bb","schema_version":"1.0","event_id":"sha256:a3d5c83188bee7c6d60caca56029f2751645f8e904190a8a8ba99a45aa3fb1bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIVC4BKDEVTXFYRQP2QKGUARMI/bundle.json","state_url":"https://pith.science/pith/NIVC4BKDEVTXFYRQP2QKGUARMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIVC4BKDEVTXFYRQP2QKGUARMI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T13:27:13Z","links":{"resolver":"https://pith.science/pith/NIVC4BKDEVTXFYRQP2QKGUARMI","bundle":"https://pith.science/pith/NIVC4BKDEVTXFYRQP2QKGUARMI/bundle.json","state":"https://pith.science/pith/NIVC4BKDEVTXFYRQP2QKGUARMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIVC4BKDEVTXFYRQP2QKGUARMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NIVC4BKDEVTXFYRQP2QKGUARMI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e63a7397adf921b934661652e88878760bca9479d3114ff504e9e94606f34ca9","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T19:12:13Z","title_canon_sha256":"cc55d665b8fa68c2d379f30007ee67a897b876aa0245867ffdb33481d8e1769c"},"schema_version":"1.0","source":{"id":"2606.07577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07577","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07577v1","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07577","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"NIVC4BKDEVTX","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"NIVC4BKDEVTXFYRQ","created_at":"2026-06-09T00:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"NIVC4BKD","created_at":"2026-06-09T00:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:a3d5c83188bee7c6d60caca56029f2751645f8e904190a8a8ba99a45aa3fb1bb","target":"graph","created_at":"2026-06-09T00:04:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.07577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual large language models (LLMs) hold strong promise for long-form video understanding, yet their long-video inference is fundamentally limited by the linear growth of video tokens and key-value (KV) caches. We present OmniMem, a memory-efficient streaming framework designed specifically for audio-visual LLMs. Unlike existing compression methods that treat all tokens uniformly, OmniMem introduces a modality-aware memory allocation strategy that separately manages visual and audio contexts, addressing the severe token imbalance between the two modalities. OmniMem further preserves info","authors_text":"Chao Zhang, Guangzhi Sun, Yixuan Li, Yudong Yang","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T19:12:13Z","title":"OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07577","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0a0d85fb2f14358444588f46abc8a1cd00c53bbc7e2a2a3bb5759d723f58add5","target":"record","created_at":"2026-06-09T00:04:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e63a7397adf921b934661652e88878760bca9479d3114ff504e9e94606f34ca9","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T19:12:13Z","title_canon_sha256":"cc55d665b8fa68c2d379f30007ee67a897b876aa0245867ffdb33481d8e1769c"},"schema_version":"1.0","source":{"id":"2606.07577","kind":"arxiv","version":1}},"canonical_sha256":"6a2a2e0543256772e2307ea0a350116232fcb3963d1da5421ee45186fc6f9035","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a2a2e0543256772e2307ea0a350116232fcb3963d1da5421ee45186fc6f9035","first_computed_at":"2026-06-09T00:04:43.565949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:43.565949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IFk8Ordd0EHq+t6PufIpUnl2lDnahMgM1T+nJBCre3qX0LfEGWEZFh4ITlnE/QAYeR09xAUAPa7o/88QiuBpDw==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:43.566619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a0d85fb2f14358444588f46abc8a1cd00c53bbc7e2a2a3bb5759d723f58add5","sha256:a3d5c83188bee7c6d60caca56029f2751645f8e904190a8a8ba99a45aa3fb1bb"],"state_sha256":"60e5c334d26ef90c3ba6325df4ff750691e664b22cd9c4ad6e238d5faf90341b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yTxBfyTc0rR+MGIkIwdnd8fMQitIroiccY5zRuXIqvO/U8EPQ67TPK4mvjyy+TnaRhzoWAB9fq1cKrxBiU5tDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T13:27:13.794277Z","bundle_sha256":"a05f2c4ecc5e65f06227235bf45f9f10b90a46ae94033dde74bb949b6bd068c6"}}